Table 1. Overview of the used layers in the indicated deep learning CNN.

In the center column, the kernel size of the corresponding layer is given. The resulting image size after layer passage is given in the rightmost column.

layer	kernel size [px2]	subimage size [px2]
input layer	-	90 × 90
conv. layer 1	21 × 21	70 × 70
reLU layer	-	70 × 70
max pooling layer	2 × 2, stride 2	35 × 35
conv. layer 2	14 × 14	22 × 22
reLU layer	-	22 × 22
max pooling layer	2 × 2, stride 2	11 × 11
conv. layer 3	6 × 6	6 × 6
reLU layer	-	6 × 6
max pooling layer	2 × 2, stride 2	3 × 3
output layer, regression type	-	1 × 1